Fractal Analysis of Digital Mammograms

Edis Đedović, Azra Gazibegović-Busuladžić, Adnan Beganović

Abstract


It has been shown that fractal analysis is useful in image processing, texture analyses and texture image segmentation. It is important to clearly detect edges of breast masses, and precisely locate individual microcalcification in mammograms. We present practical help in that area by fractal analysis, using the concept of fractional Brownian motion. It can be shown that there is a correlation between specific quantitative result of such analysis (Hurst coefficient) and the type of breast mass or tumor.
Keywords: digital mammograms, image segmentation, fractals, fractional Brownian motion, Hurst coefficient.


Full Text:

PDF

References


Pentland A. Fractal-based description of natural scenes.

IEEE Trans Pattern Anal Mach Intell 1984;6(6):661– 74.

DR Chen, RF Chang, CJ Chen, MF Ho, SJ Kuo,ST Chen,

SJ Hung, WK Moon: Classification of breast ultrasound

images using fractal feature. ELSEVIER Journal of Clinical

Imaging 29 (2005) 235–245.

Rafael C. Gonzalez, Richard E. Woods: Digital Image Processing,

Second Edition. Prentice Hall (2009).

Chen CC, Daponte JS, Fox MD. Fractal feature analysis

and classification in medical imaging. IEEE Trans Med Imag

(2) (1989):133– 42.


Refbacks

  • There are currently no refbacks.